Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1408-1419
Paul Aazagreyir, Peter Appiahene, Obed Appiah, Samuel Boateng
This research aims to compare and analyze the effectiveness of four popular fuzzy multi-criteria decision-making methods (FMCDMMs) for quality of service (QoS)-based web service selection. These methods are fuzzy DEMATEL (FD), fuzzy TOPSIS (FT), fuzzy VIKOR (FV), and fuzzy PROMETHEE (FP), including three ranking versions of FV. We assess the ranking similarities among these methods using Spearman's relationship figure. We describe the algorithms of these six FMCDMs in the methods section. In a case study, we collected primary data from five experts who rated nine QoS factors of nine web services. We used modified online software for analysis. The results showed that S6 ranked first in all FMCDMs, except for FD and FP, where it was ranked 2nd and 8th, respectively. The highest association coefficient (Rs) was found between FT and FV ranking in S techniques (0.983), FV ranking in S and FV ranking in Q (0.883), and FT and FV ranking Q (0.833) when comparing the similarity measure of the FMCDMMs. This analysis helps decision-makers and researchers choose the most suitable methods for integrated FMCDMs studies and real-world problem-solving.
{"title":"Comparative analysis of fuzzy multi-criteria decision-making methods for quality of service-based web service selection","authors":"Paul Aazagreyir, Peter Appiahene, Obed Appiah, Samuel Boateng","doi":"10.11591/ijai.v13.i2.pp1408-1419","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1408-1419","url":null,"abstract":"This research aims to compare and analyze the effectiveness of four popular fuzzy multi-criteria decision-making methods (FMCDMMs) for quality of service (QoS)-based web service selection. These methods are fuzzy DEMATEL (FD), fuzzy TOPSIS (FT), fuzzy VIKOR (FV), and fuzzy PROMETHEE (FP), including three ranking versions of FV. We assess the ranking similarities among these methods using Spearman's relationship figure. We describe the algorithms of these six FMCDMs in the methods section. In a case study, we collected primary data from five experts who rated nine QoS factors of nine web services. We used modified online software for analysis. The results showed that S6 ranked first in all FMCDMs, except for FD and FP, where it was ranked 2nd and 8th, respectively. The highest association coefficient (Rs) was found between FT and FV ranking in S techniques (0.983), FV ranking in S and FV ranking in Q (0.883), and FT and FV ranking Q (0.833) when comparing the similarity measure of the FMCDMMs. This analysis helps decision-makers and researchers choose the most suitable methods for integrated FMCDMs studies and real-world problem-solving.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"83 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1992-2002
A. Machmudah, E. A. Bakar, Ranjendran R, Wibowo Harso Nugroho, M. I. Solihin, Abdul Ghofur
Reducing a gas emission of shipping transportations become a main goal of international maritime organization to achieve a clean energy. One of best scenarios to achieve this goal is to shift a fossil fuel to a renewable energy-based fuel of a ship propulsion. This paper studies an optimization of a control system of the renewable-based small gas turbine engine for the ship propulsion. Proposed control system consists of a proportional-integral with engine performance limiters to avoid an engine damage. Proportional-integral gains are tuned by a whale optimization algorithm. A gain scheduling analysis of a step response is performed to obtain a searching area of tuning parameters and values of constant gains. In this step, the gains are modeled as function of plant variables. After the searching area is obtained, the proportional-integral gains are optimized using the whale optimization algorithm while the additional gains are set as constant values. Using this scenario, stable and optimal gains have been successfully achieved. Results show that the proposed method has better performance than that of the previous methods, i.e. gain scheduling and gain scheduling optimized by the whale optimization algorithm. The proposed method has lowest fitness value and does not have an overshoot problem.
{"title":"Control system optimisation of biodiesel-based gas turbine for ship propulsion","authors":"A. Machmudah, E. A. Bakar, Ranjendran R, Wibowo Harso Nugroho, M. I. Solihin, Abdul Ghofur","doi":"10.11591/ijai.v13.i2.pp1992-2002","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1992-2002","url":null,"abstract":"Reducing a gas emission of shipping transportations become a main goal of international maritime organization to achieve a clean energy. One of best scenarios to achieve this goal is to shift a fossil fuel to a renewable energy-based fuel of a ship propulsion. This paper studies an optimization of a control system of the renewable-based small gas turbine engine for the ship propulsion. Proposed control system consists of a proportional-integral with engine performance limiters to avoid an engine damage. Proportional-integral gains are tuned by a whale optimization algorithm. A gain scheduling analysis of a step response is performed to obtain a searching area of tuning parameters and values of constant gains. In this step, the gains are modeled as function of plant variables. After the searching area is obtained, the proportional-integral gains are optimized using the whale optimization algorithm while the additional gains are set as constant values. Using this scenario, stable and optimal gains have been successfully achieved. Results show that the proposed method has better performance than that of the previous methods, i.e. gain scheduling and gain scheduling optimized by the whale optimization algorithm. The proposed method has lowest fitness value and does not have an overshoot problem.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"55 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1711-1722
Qusai Q. Abuein, M. Shatnawi, Nour Alqudah
This study introduces a novel approach to streamline the recruitment process, benefiting both employers and job seekers. It leverages real-time personality-based classification to match candidates with the most suitable roles in a scalable and precise manner. This is achieved through machine learning-driven hyper-personalization, employing deep learning models to create a predictive language model. The study encompasses two key tasks: binary classification, distinguishing sentences containing soft skills (1) from those that do not (0), and multi-class classification, categorizing positive sentences into five classes based on Big Five personality traits. The research involved a series of experiments. Initially, multiple machine learning algorithms were employed to establish baseline models. Subsequently, the study investigated the impact of deep learning versus these baseline models. The results demonstrated an accuracy of 0.79% and 0.68% for binary classification tasks, and 0.79% and 0.60% for multi-class classification tasks, using Support Vector Machines in the machine learning task, and Bidirectional Long Short-Term Memory in the deep learning task, respectively. This approach showcases promise in revolutionizing the job matching process, offering a more efficient and accurate means of connecting individuals with their ideal employment opportunities based on their unique soft skills and personality traits.
{"title":"Improving job matching with deep learning-based hyper-personalization","authors":"Qusai Q. Abuein, M. Shatnawi, Nour Alqudah","doi":"10.11591/ijai.v13.i2.pp1711-1722","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1711-1722","url":null,"abstract":"This study introduces a novel approach to streamline the recruitment process, benefiting both employers and job seekers. It leverages real-time personality-based classification to match candidates with the most suitable roles in a scalable and precise manner. This is achieved through machine learning-driven hyper-personalization, employing deep learning models to create a predictive language model. The study encompasses two key tasks: binary classification, distinguishing sentences containing soft skills (1) from those that do not (0), and multi-class classification, categorizing positive sentences into five classes based on Big Five personality traits. The research involved a series of experiments. Initially, multiple machine learning algorithms were employed to establish baseline models. Subsequently, the study investigated the impact of deep learning versus these baseline models. The results demonstrated an accuracy of 0.79% and 0.68% for binary classification tasks, and 0.79% and 0.60% for multi-class classification tasks, using Support Vector Machines in the machine learning task, and Bidirectional Long Short-Term Memory in the deep learning task, respectively. This approach showcases promise in revolutionizing the job matching process, offering a more efficient and accurate means of connecting individuals with their ideal employment opportunities based on their unique soft skills and personality traits.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"40 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1479-1488
Doraisamy Radha, Minal Moharir
An increase in the number of cores gives a significant bounce in performance than an improvement in any of the factors or hardware. Many core systems use network-on-chip (NoC) for efficient communications among the cores in the system. However, the problem with NoC-based communication is that it significantly consumes a large amount of power and energy because the number of routers increases with the increase in the number of cores in the system. Power consumed by such components leads to degradation of the performance. The placement of cores in the topology is non-deterministic polynomial-time hardness (NP-Hard) problem. The optimal placement of cores in NoC is essential as it minimizes latency and communication costs. Thus, the NP-Hard problem of placing cores is solved using genetic algorithm (GA) based quadtree topology. The proposed work shows the analysis of GA-based quadtree topology, which outperforms other topologies in most aspects. The performance evaluation of GA-based quadtree topology is based on latency, throughput, power, area, bisection bandwidth, and diameter. Comparing these parameters with other topologies shows the prominence of the quadtree topology. The evaluation is performed in the Booksim simulator, and the experimental results revealed that the proposed GA-based quad tree-based topology is efficient for NoC-based communications.
内核数量的增加比任何因素或硬件的改进都能显著提升性能。许多内核系统使用片上网络（NoC）实现系统内核间的高效通信。然而，基于 NoC 的通信存在的问题是，由于路由器的数量会随着系统内核数量的增加而增加，因此会大量消耗电力和能源。这些组件消耗的功率会导致性能下降。在拓扑结构中放置内核是一个非确定性多项式时间困难（NP-Hard）问题。内核在 NoC 中的最佳位置至关重要，因为它能最大限度地减少延迟和通信成本。因此，基于四叉树拓扑结构的遗传算法（GA）解决了放置内核的 NP-Hard 问题。本论文展示了对基于 GA 的四叉树拓扑结构的分析，该拓扑结构在大多数方面都优于其他拓扑结构。基于 GA 的四叉树拓扑的性能评估基于延迟、吞吐量、功耗、面积、分段带宽和直径。将这些参数与其他拓扑结构进行比较，可以看出四叉树拓扑结构的优势。评估在 Booksim 仿真器中进行，实验结果表明，所提出的基于 GA 的四叉树拓扑结构在基于 NoC 的通信中是高效的。
{"title":"Evaluation of genetic algorithm in network-on-chip based architecture","authors":"Doraisamy Radha, Minal Moharir","doi":"10.11591/ijai.v13.i2.pp1479-1488","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1479-1488","url":null,"abstract":"An increase in the number of cores gives a significant bounce in performance than an improvement in any of the factors or hardware. Many core systems use network-on-chip (NoC) for efficient communications among the cores in the system. However, the problem with NoC-based communication is that it significantly consumes a large amount of power and energy because the number of routers increases with the increase in the number of cores in the system. Power consumed by such components leads to degradation of the performance. The placement of cores in the topology is non-deterministic polynomial-time hardness (NP-Hard) problem. The optimal placement of cores in NoC is essential as it minimizes latency and communication costs. Thus, the NP-Hard problem of placing cores is solved using genetic algorithm (GA) based quadtree topology. The proposed work shows the analysis of GA-based quadtree topology, which outperforms other topologies in most aspects. The performance evaluation of GA-based quadtree topology is based on latency, throughput, power, area, bisection bandwidth, and diameter. Comparing these parameters with other topologies shows the prominence of the quadtree topology. The evaluation is performed in the Booksim simulator, and the experimental results revealed that the proposed GA-based quad tree-based topology is efficient for NoC-based communications.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"85 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2364-2373
Sathya Vijaykumar, Shiva Prakash Thyagaraj
Multimedia traffic in Internet of Things applications is generated for various purposes and encompasses a wide range of multimedia data, including video streams, audio files, images, and sensor data. Network providers employ various strategies to handle multimedia traffic in IoT applications efficiently. But most of these methods have not considered optimizing the RTSP (Real-Time Streaming Protocol), RTP (Real-time Transport Protocol), and RTCP (Real-Time Control Protocol) to improve the throughput and QoS of the IoT applications. Hence, in this Congestion and Throughput Optimization Protocol (CTOP) work, we present a model which optimizes the RTSP, RTP, and RTCP protocol to improve the throughput and QoS. The CTOP model outperforms the Big Packet Protocol model in terms of average throughput, multimedia loss, delay, and energy consumption for both less and high-traffic scenarios. For less-level of traffic and high level of traffic, the CTOP model achieves a better average throughput, and average multimedia delay, reducing the average multimedia loss and average energy consumption in comparison to the existing BBP model. These results highlight the improved performance and efficiency of the CTOP model compared to the BBP model.
{"title":"Congestion and throughput optimization protocol for providing better quality of service and experience","authors":"Sathya Vijaykumar, Shiva Prakash Thyagaraj","doi":"10.11591/ijai.v13.i2.pp2364-2373","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2364-2373","url":null,"abstract":"Multimedia traffic in Internet of Things applications is generated for various purposes and encompasses a wide range of multimedia data, including video streams, audio files, images, and sensor data. Network providers employ various strategies to handle multimedia traffic in IoT applications efficiently. But most of these methods have not considered optimizing the RTSP (Real-Time Streaming Protocol), RTP (Real-time Transport Protocol), and RTCP (Real-Time Control Protocol) to improve the throughput and QoS of the IoT applications. Hence, in this Congestion and Throughput Optimization Protocol (CTOP) work, we present a model which optimizes the RTSP, RTP, and RTCP protocol to improve the throughput and QoS. The CTOP model outperforms the Big Packet Protocol model in terms of average throughput, multimedia loss, delay, and energy consumption for both less and high-traffic scenarios. For less-level of traffic and high level of traffic, the CTOP model achieves a better average throughput, and average multimedia delay, reducing the average multimedia loss and average energy consumption in comparison to the existing BBP model. These results highlight the improved performance and efficiency of the CTOP model compared to the BBP model.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"114 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2173-2184
Imad Zyout, Mo’ath Zyout
Sentiment analysis systems aim to assess people’s opinions across various domains by collecting and categorizing feedback and reviews. In our study, researchers put forward a sentiment analysis system that leverages three distinct embedding techniques: automatic, global vectors (GloVe) for word representation, and bidirectional encoder representations from transformers (BERT). This system features an attention layer, with the best model chosen through rigorous comparisons. In developing the sentiment analysis model, we employed a hybrid dataset comprising students’ feedback and comments. This dataset comprises 3,820 comments, including 2,773 from formal evaluations and 1,047 generated by ChatGPT and prompting engineering. Our main motivation for integrating generative AI was to balance both positive and negative comments. We also explored recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional long short-term memory (Bi-LSTM), with and without pre-trained GloVe embedding. These techniques produced F-scores ranging from 67% to 69%. On the other hand, the sentiment model based on BERT, particularly its KERAS implementation, achieved higher F-scores ranging from 83% to 87%. The Bi-LSTM architecture outperformed other models and the inclusion of an attention layer further enhanced the performance, resulting in F-scores of 89% and 88% from the Bi-LSTM-BERT sentiment models, respectively.
情感分析系统旨在通过收集反馈和评论并对其进行分类，评估人们在不同领域的观点。在我们的研究中，研究人员提出了一种情感分析系统，该系统利用了三种不同的嵌入技术：自动嵌入、用于单词表示的全局向量（GloVe）以及来自变换器的双向编码器表示（BERT）。该系统有一个关注层，通过严格的比较选出最佳模型。在开发情感分析模型时，我们采用了一个由学生反馈和评论组成的混合数据集。该数据集包含 3,820 条评论，其中 2,773 条来自正式评价，1,047 条由 ChatGPT 和提示工程生成。我们整合生成式人工智能的主要动机是平衡正面和负面评论。我们还探索了递归神经网络 (RNN)、门控递归单元 (GRU)、长短期记忆 (LSTM) 和双向长短期记忆 (Bi-LSTM)，并使用和不使用预先训练的 GloVe 嵌入。这些技术产生的 F 分数从 67% 到 69% 不等。另一方面，基于 BERT 的情感模型，特别是其 KERAS 实现，取得了更高的 F 分数，从 83% 到 87%。Bi-LSTM 架构的性能优于其他模型，而加入注意力层则进一步提高了性能，因此 Bi-LSTM-BERT 情感模型的 F 分数分别达到了 89% 和 88%。
{"title":"Sentiment analysis of student feedback using attention-based RNN and transformer embedding","authors":"Imad Zyout, Mo’ath Zyout","doi":"10.11591/ijai.v13.i2.pp2173-2184","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2173-2184","url":null,"abstract":"Sentiment analysis systems aim to assess people’s opinions across various domains by collecting and categorizing feedback and reviews. In our study, researchers put forward a sentiment analysis system that leverages three distinct embedding techniques: automatic, global vectors (GloVe) for word representation, and bidirectional encoder representations from transformers (BERT). This system features an attention layer, with the best model chosen through rigorous comparisons. In developing the sentiment analysis model, we employed a hybrid dataset comprising students’ feedback and comments. This dataset comprises 3,820 comments, including 2,773 from formal evaluations and 1,047 generated by ChatGPT and prompting engineering. Our main motivation for integrating generative AI was to balance both positive and negative comments. We also explored recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional long short-term memory (Bi-LSTM), with and without pre-trained GloVe embedding. These techniques produced F-scores ranging from 67% to 69%. On the other hand, the sentiment model based on BERT, particularly its KERAS implementation, achieved higher F-scores ranging from 83% to 87%. The Bi-LSTM architecture outperformed other models and the inclusion of an attention layer further enhanced the performance, resulting in F-scores of 89% and 88% from the Bi-LSTM-BERT sentiment models, respectively.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"5 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1557-1566
S. Merzouk, S. Bouhsissin, Touria Hamim, N. Sael, A. Marzak
Agile methods are widely known in different companies, including information technology (IT) companies. They appeared intending to solve the problems of traditional methods while proposing an iterative and incremental cycle. These methods consist of four values and the twelve principles agreed upon in 2001 in a Manifesto. However, each method holds singularities from which it is difficult to choose one to adopt in different project cases. The selection of the method to adopt positively or negatively affects the final product following the criteria of the project and the personnel. Project experts must research and compare methods manually to make a choice, a thing that drains time, which is a key factor in project realization. Currently, there is no intelligent system or model that allows choosing the agile method to adopt for such a project. For this purpose, artificial intelligence (AI) techniques will be used to develop a Chatbot that allows reaching the aim. This Chatbot will be developed based on a decision tree model that will be proposed from an experimental study.
{"title":"Artificial intelligence for choosing an agile method","authors":"S. Merzouk, S. Bouhsissin, Touria Hamim, N. Sael, A. Marzak","doi":"10.11591/ijai.v13.i2.pp1557-1566","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1557-1566","url":null,"abstract":"Agile methods are widely known in different companies, including information technology (IT) companies. They appeared intending to solve the problems of traditional methods while proposing an iterative and incremental cycle. These methods consist of four values and the twelve principles agreed upon in 2001 in a Manifesto. However, each method holds singularities from which it is difficult to choose one to adopt in different project cases. The selection of the method to adopt positively or negatively affects the final product following the criteria of the project and the personnel. Project experts must research and compare methods manually to make a choice, a thing that drains time, which is a key factor in project realization. Currently, there is no intelligent system or model that allows choosing the agile method to adopt for such a project. For this purpose, artificial intelligence (AI) techniques will be used to develop a Chatbot that allows reaching the aim. This Chatbot will be developed based on a decision tree model that will be proposed from an experimental study.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"18 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2283-2290
Yousheng Gao, Raihah Aminuddin, Raseeda Hamzah, Li Ang, Siti Khatijah Nor Abdul Rahim
In the absence of supervisory information in spectral clustering algorithms, it is difficult to construct suitable similarity graphs for data with complex shapes and varying densities. To address this issue, this paper proposes a Semi-supervised Spectral Clustering algorithm based on shared nearest neighbor. The proposed algorithm combines the idea of semi-supervised clustering, adding Shared Nearest Neighbor information to the calculation of the distance matrix, and using pairwise constraint information to find the relationship between two data points, while providing a portion of supervised information. Comparative experiments were conducted on artificial data sets and University of California Irvine machine learning repository datasets. The experimental results show that the proposed algorithm achieves better clustering results compared to traditional K-means and spectral clustering algorithms.
{"title":"Semi-supervised spectral clustering using shared nearest neighbour for data with different shape and density","authors":"Yousheng Gao, Raihah Aminuddin, Raseeda Hamzah, Li Ang, Siti Khatijah Nor Abdul Rahim","doi":"10.11591/ijai.v13.i2.pp2283-2290","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2283-2290","url":null,"abstract":"In the absence of supervisory information in spectral clustering algorithms, it is difficult to construct suitable similarity graphs for data with complex shapes and varying densities. To address this issue, this paper proposes a Semi-supervised Spectral Clustering algorithm based on shared nearest neighbor. The proposed algorithm combines the idea of semi-supervised clustering, adding Shared Nearest Neighbor information to the calculation of the distance matrix, and using pairwise constraint information to find the relationship between two data points, while providing a portion of supervised information. Comparative experiments were conducted on artificial data sets and University of California Irvine machine learning repository datasets. The experimental results show that the proposed algorithm achieves better clustering results compared to traditional K-means and spectral clustering algorithms.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"10 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1398-1407
Tajul Rosli Razak, Ahmad Zia Ul-Saufie, Mohamad Hanis Yusoff, Mohammad Hafiz Ismail, Shukor Sanim Mohd Fauzi, N. A. Mohd Zaki
Nowadays, improvements in diabetes detection that provide patients with vital information are needed. This is due to the fact that Diabetes mellitus has generated a worldwide epidemic that costs society and people. Also, patients tend to misread symptoms, and clinicians who collect insufficient data may produce erroneous outcomes. Therefore, this study aims to demonstrate that a programme that integrates expert advice such as decisions, recommendations, or solutions is an excellent method for reducing the incidence of diabetes. Specifically, this study intends to implement a fuzzy expert system that can detect and report the early stages of diabetes as a viable approach. Furthermore, since this programme is available to everyone, people may easily self-diagnose themselves if they have a blood glucose monitoring device. However, developing the fuzzy expert system for real-world situations, such as diabetes patients, using any programming tools is not straightforward. Therefore, this study will provide a comprehensive approach to constructing a fuzzy expert system using the popular programming language Python.
{"title":"Python scikit-fuzzy: developing a fuzzy expert system for diabetes diagnosis","authors":"Tajul Rosli Razak, Ahmad Zia Ul-Saufie, Mohamad Hanis Yusoff, Mohammad Hafiz Ismail, Shukor Sanim Mohd Fauzi, N. A. Mohd Zaki","doi":"10.11591/ijai.v13.i2.pp1398-1407","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1398-1407","url":null,"abstract":"Nowadays, improvements in diabetes detection that provide patients with vital information are needed. This is due to the fact that Diabetes mellitus has generated a worldwide epidemic that costs society and people. Also, patients tend to misread symptoms, and clinicians who collect insufficient data may produce erroneous outcomes. Therefore, this study aims to demonstrate that a programme that integrates expert advice such as decisions, recommendations, or solutions is an excellent method for reducing the incidence of diabetes. Specifically, this study intends to implement a fuzzy expert system that can detect and report the early stages of diabetes as a viable approach. Furthermore, since this programme is available to everyone, people may easily self-diagnose themselves if they have a blood glucose monitoring device. However, developing the fuzzy expert system for real-world situations, such as diabetes patients, using any programming tools is not straightforward. Therefore, this study will provide a comprehensive approach to constructing a fuzzy expert system using the popular programming language Python.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"88 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141230571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1925-1934
Ossama Cherkaoui, H. Anoun, A. Maizate
Health insurance fraud is a complex problem that also has a significant financial impact. Recently, with the availability of large volumes of data and the evolution of computing power, machine learning techniques have become the preferred method for fraud detection. However, the main difficulty facing researchers in this field is the lack of real data sets and the absence of reliable fraud labels. Most published studies use aggregated provider-level or simulated data to test fraud detection algorithms, which may not deliver accurate results. The present study aims to provide a more accurate assessment of fraud detection methods by using real detailed health insurance claims data to compare six of the most common supervised classification algorithms including neural networks and the use of two categorical feature preparation methods. The study was conducted under the guidance of insurance experts, who provided the fraud label inference rules and reviewed the results. A comprehensive description of the benchmarking process and an interpretation of the results are provided in this paper. The results show that supervised classification can be used effectively to detect health insurance fraud, improving detection accuracy by a factor of 4.2 (84% recall for a positive rate of 20%).
{"title":"A benchmark of health insurance fraud detection using machine learning techniques","authors":"Ossama Cherkaoui, H. Anoun, A. Maizate","doi":"10.11591/ijai.v13.i2.pp1925-1934","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1925-1934","url":null,"abstract":"Health insurance fraud is a complex problem that also has a significant financial impact. Recently, with the availability of large volumes of data and the evolution of computing power, machine learning techniques have become the preferred method for fraud detection. However, the main difficulty facing researchers in this field is the lack of real data sets and the absence of reliable fraud labels. Most published studies use aggregated provider-level or simulated data to test fraud detection algorithms, which may not deliver accurate results. The present study aims to provide a more accurate assessment of fraud detection methods by using real detailed health insurance claims data to compare six of the most common supervised classification algorithms including neural networks and the use of two categorical feature preparation methods. The study was conducted under the guidance of insurance experts, who provided the fraud label inference rules and reviewed the results. A comprehensive description of the benchmarking process and an interpretation of the results are provided in this paper. The results show that supervised classification can be used effectively to detect health insurance fraud, improving detection accuracy by a factor of 4.2 (84% recall for a positive rate of 20%). ","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"47 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：